5 papers · 1 filter
Multilingual Safety Alignment Via Sparse Weight Editing
Jiaming Liang, Zhaoxin Wang, Handing Wang
Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-reso…
SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
Zhaoxin Wang, Jiaming Liang, Fengbin Zhu +5
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behavio…
Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
Zhaoxin Wang, Handing Wang, Cong Tian +1
Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attac…
Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
Zhaoxin Wang, Handing Wang, Cong Tian +1
Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak at…
Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
Zhaoxin Wang, Handing Wang, Cong Tian +1
Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT…